© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8081
    Prev
    Next
    INDEX
    Explanations

    small numerical values like quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to the number fifteen in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    é¾į
    -0.68
    aji
    -0.67
    gow
    -0.65
     fundament
    -0.64
    ãĥ¢
    -0.61
    Malley
    -0.61
     flowed
    -0.60
    worms
    -0.59
    ulty
    -0.59
    ãĥĩ
    -0.58
    POSITIVE LOGITS
     15
    2.83
     14
    2.29
     16
    2.27
     17
    2.14
     13
    2.13
     25
    2.02
     20
    1.98
     35
    1.92
     12
    1.92
     19
    1.91
    Activations Density 0.091%

    No Known Activations